New automated screening technique accelerates biological image analysis

May 1, 2008, Pittsburgh, PA--Researchers in Carnegie Mellon University's Lane Center for Computational Biology have discovered how to significantly speed up critical steps in an automated method for analyzing cell cultures and other biological specimens.

The new technique, published online in the Journal of Machine Learning Research, http://jmlr.csail.mit.edu/, promises to enable higher accuracy analysis of the microscopic images produced by today's high-throughput biological screening methods, such as the ones used in drug discovery, and to help decipher the complex structure of human tissues.

Improved accuracy could reduce the cost and the time necessary for these screening methods, make possible new types of experiments that previously would have required an infeasible amount of resources, and perhaps uncover interesting but subtle anomalies that otherwise would go undetected, the researchers said.

The technique also will be applicable in fields beyond biology because it improves the efficiency of the belief propagation algorithm, a widely used method for drawing conclusions about interconnected networks.

"Current automated screening systems for examining cell cultures look at individual cells and do not fully consider the relationships between neighboring cells," said Geoffrey Gordon, associate research professor in the School of Computer Science's Machine Learning Department. "This is in large part because simultaneously examining many cells with existing methods requires impractical amounts of computational time."

In many cases, computer vision systems have been shown to distinguish patterns that are difficult for humans to detect, he added. However, even automated systems may confuse two similar patterns, and the confusion may be resolvable by considering neighboring cells.

Gordon and his fellow authors, biomedical engineering student Shann-Ching "Sam" Chen and computational biologist Robert F. Murphy, were able to expand their focus from single to multiple cells by increasing the efficiency of the belief propagation algorithm. The algorithm has become a workhorse for researchers because it enables a computer to make inferences about a set of data by drawing on multiple sources of information. In the case of biological specimens, for instance, it can be used to infer which parts of the image are individual cells or to determine whether the distributions of particular proteins within each cell are abnormal.

But as the number of variables increase, the belief propagation algorithm can grow unwieldy and require an impractical amount of computing time to solve these problems.

The belief propagation algorithm assumes that neighbors--whether they are cells or bits of text--have effects on each other. So the algorithm represents each piece of evidence used to make inferences as a node in an interconnected network, and exchanges messages between nodes. The Carnegie Mellon researchers found shortcuts for generating these messages, which significantly improved the speed of the entire network.

Murphy, director of the Lane Center for Computational Biology, said this technique could improve the performance of belief propagation algorithms in many applications, including text analysis, Web analysis and medical diagnosis. For this paper, the researchers applied their techniques to analysis of protein patterns within HeLa cells. They found the technique speeded analysis by several orders of magnitude.

In high-throughput screening processes used for drug discovery and other research, tens of thousands of wells--each containing tens or hundreds of cells--need to be analyzed each day, Murphy said. Automated analysis of the cellular relationships within so many wells would be impossible without the sort of speedups achieved in the new study, he added.

Get All the BioOptics World News Delivered to Your Inbox

Subscribe to BioOptics World Magazine or email newsletter today at no cost and receive the latest news and information.

 Subscribe Now
Related Articles

NANOTECHNOLOGY/LIGHT ACTIVATION: IR light method turns blood clotting on (like drugs) and off (like nothing else)

Gold nanoparticles, controlled by infrared (IR) light from a pulsed femtosecond laser, promise to promote wound healing and help doctors control blood clotting in patients undergoing surgery.

Microscopy helps discover potential new drug target for cystic fibrosis

An international team of scientists, using automated microscopy and genetics, have discovered a promising potential drug target for cystic fibrosis.

Next-gen DNA sequencing helps provide new genetic clue to anorexia

The largest next-generation DNA sequencing study of anorexia nervosa to date has linked the eating disorder to variants in a gene coding for an enzyme that regulates cholesterol metabolism.

Synchrotron light identifies RNA double helix structure

Scientists at McGill University have crystallized a short RNA sequence, poly (rA)11, and used data collected at the Canadian Light Source (CLS) and the Cornell High Energy Synchrotron to confirm th...

BLOGS

Neuro15 exhibitors meet exacting demands: Part 2

Increasingly, neuroscientists are working with researchers in disciplines such as chemistry and p...

Why be free?

A successful career contributed to keeping OpticalRayTracer—an optical design software program—fr...

LASER Munich 2015 is bio-bent

LASER World of Photonics 2015 included the European Conferences on Biomedical Optics among its si...

White Papers

Understanding Optical Filters

Optical filters can be used to attenuate or enhance an image, transmit or reflect specific wavele...

How can I find the right digital camera for my microscopy application?

Nowadays, image processing is found in a wide range of optical microscopy applications. Examples ...

CONNECT WITH US

            

Twitter- BioOptics World

Copyright © 2007-2016. PennWell Corporation, Tulsa, OK. All Rights Reserved.PRIVACY POLICY | TERMS AND CONDITIONS